GET

/v1/schemas/perplexity/chat/v1%2Fagent

kind inputactivity chathash f1b1e4ff…extracted Nov 20, 2026version currentsource upstream spec ↗

Request body

22 properties · 1 required · 45 $defs
propertytypedescriptionconstraints
input*string | InputItem[]Input content - either a string or array of input items
backgroundbooleanRun the response asynchronously. With `stream: false`, the request returns immediately with `status: "queued"`; poll `GET /v1/responses/{id}` until the response reaches a terminal status. Background runs are durable, so you can also stream them and reconnect a…
instructionsstringSystem instructions for the model
language_preferencestringISO 639-1 language code for response language
max_output_tokensintegerOptional total output-token budget across the run, including for Anthropic models. When neither the request nor its effort level or saved profile supplies a budget, each generation can produce up to 128,000 output tokens, capped by the model's supported limit.n ≥ 1 · format: int32
max_stepsintegerMaximum number of research loop steps. If provided, overrides the effort level's max_steps value. For requests that specify model or models without an effort level, the default is 1. Set max_steps to at least 3 when using finance_search with a direct model so …1 ≤ n ≤ 500 · format: int32
modelstringModel ID in provider/model format (e.g., "openai/gpt-5.6-terra", "anthropic/claude-sonnet-5-5"). If models is also provided, models takes precedence. Required if neither models nor effort is provided.
modelsstring[]Model fallback chain. Each model is in provider/model format. Models are tried in order until one succeeds. Max 5 models allowed. If set, takes precedence over single model field. The response.model will reflect the model that actually succeeded.items ≥ 1 · items ≤ 5
effortstringEffort to run, as `name`, `name@latest`, or `name@<version>` (e.g., "fast", "low", "fast@2026-09-29.0"). An effort level is a pre-configured model with system prompt and search parameters. `name` and `name@latest` run the active version. `name@<version>` runs …
profileProfileReferenceSaved, versioned configuration to run with. The version is resolved when the request is admitted. Cannot be combined with effort.
previous_response_idstringOpenAI-compatible previous response id for multi-turn response chains. When set, the new response continues from the completed prior response's saved state. The prior response must belong to the same account and have completed.
prompt_cache_keystringStable key for prompt cache affinity. Send the same key on requests that share a prompt prefix, including retries and multi-turn conversations, so later requests can read the cached prefix. The key is scoped to your account and does not affect model routing. S…
prompt_cache_optionsPromptCacheOptionsPrompt cache options. `implicit` (default) keeps the default cache breakpoints and provider automatic caching. `explicit` turns both off, so only `input_text` parts marked with `prompt_cache_breakpoint` are cached; with no marks, the request makes no cache wri…
reasoningReasoningConfig
response_formatResponseFormatSpecifies the desired output format for the model response
storebooleanOpenAI-compatible storage toggle. When false, the response is hidden from later retrieve calls, and the echoed response reports `store: false`. It can still be used as a `previous_response_id` continuation source.
streambooleanIf true, returns SSE stream instead of JSON
toolsTool[]Tools available to the model
tool_choiceenum | objectTool choice strategy. Use `{"type":"image_search"}` to force image search.
skillsSkill[]Built-in, request-scoped inline, and organization-owned custom skills available to the model. Skill metadata is disclosed to the model up front; full instructions are loaded on demand through the load_skill tool. Selecting any skill enables the sandbox tool fo…items ≤ 16
temperaturenumberOpenAI-compatible sampling temperature forwarded to generation.0 ≤ n ≤ 2 · format: double
top_pnumberOpenAI-compatible nucleus sampling parameter forwarded to generation.0 ≤ n ≤ 1 · format: double

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"perplexity","endpointId":"v1/agent","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}